© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 7036
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dictionary items iteration

    python-code · gemini-2.5-flash-lite

    `_node` followed by `.` or `(` (negative activations)

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uristic
    -0.18
     heuristic
    -0.16
     colle
    -0.16
    rontier
    -0.15
    oal
    -0.13
     goal
    -0.11
    blem
    -0.11
    istic
    -0.09
    uccess
    -0.09
     cost
    -0.09
    POSITIVE LOGITS
    if
    0.07
    fset
    0.06
    :-
    0.05
    ð
    0.05
     by
    0.05
    _by
    0.05
    _capacity
    0.05
    .in
    0.04
    xtend
    0.04
    _solution
    0.04
    Activations Density 100.000%

    No Known Activations